def save_comparison_table(table, extractors, classifiers, filepath):
'''
Exports the data contained in the table to csv format:
by def: each row represent a different set of feature
each column represent a different kind of classifier
'''
file = open(filepath, 'w')
header = ','.join(['Features\\Classifier'] +
[get_classifier_name(clf) for clf in classifiers]) + '\n'
file.write(header)
for idx, row in enumerate(table):
str_row = get_features_extr_name(extractors[idx]) + ","
str_row += ','.join(['{0:.3f}'.format(float(x)) for x in row]) + '\n'
file.write(str_row)
file.close()
def train(inputPath, splitsPath, outputPath, verbosity_level=1):
'''
For each language, proceeds as follow:
- takes in input the corresponding .pkl file
- train a text-based classifier on the 80% split
- save the resulting model in outputPath
:param inputPath: Path to PAN18 dataset
:param splitsPath: Path to dir containing the .pkl files produced by 'splitting.py'
:param outputPath: Path to dir in which the outputs models will be saved
NB. Create outputPath directory before using this function
'''
for lang in ['ar', 'en', 'es']:
input_dir = join(inputPath, lang)
output_dir = join(outputPath, lang)
#print("input_dir ", input_dir)
#print("output_dir ", output_dir)
if exists(output_dir):
rmtree(output_dir)
makedirs(output_dir)
# --------------------------------------------------------------------------
# Load the .pkl file
with open(splitsPath + "/" + lang + ".pkl", 'rb') as f:
dic = load(f)
# Load the tweets in one language
Authors = parse_tweets_from_dir(input_dir=inputPath + "/" + lang + "/",
label=True,
aggregation=100,
splitDic=dic,
verbosity_level=verbosity_level)
if not (Authors):
abort_clean("Tweets loading failed")
# --------------------------------------------------------------------------
# Load the classifier
t0 = time()
classifier = get_classifier(classifier_str="svm",
config=None,
verbose=verbosity_level)
# --------------------------------------------------------------------------
# Load the features extractors
features_extr = None
features_extr = get_features_extr(features_str_list="tfidf",
language=lang,
verbose=verbosity_level)
# --------------------------------------------------------------------------
# Build the execution pipeline
pipeline = get_pipeline(features_extr=features_extr,
classifier=classifier,
verbose=verbosity_level)
# --------------------------------------------------------------------------
# Train the execution pipeline
# train and cross validate results
if (verbosity_level):
print("Model Training with cross validation\n")
pipeline, scores, best_train_indices, best_test_indices = train_model_cross_validation(
authors=Authors,
label_type="gender",
pipeline=pipeline,
verbose=verbosity_level)
if verbosity_level:
print_scores(scores)
filename = str(
get_features_extr_name(features_extr) + "+" +
get_classifier_name(classifier))
save_scores(scores=scores,
output_dir=output_dir + "/",
filename=lang,
verbose=verbosity_level)
#--------------------------------------------------------------------------
# Save the resulting model
filename = str(
get_features_extr_name(features_extr) + "+" +
get_classifier_name(classifier))
# build train corpus
authors = array(Authors)
train_authors = authors[best_train_indices]
train_corpus = build_corpus(authors=train_authors,
label_type='gender',
verbosity=verbosity_level)
# build test corpus
test_authors = authors[best_test_indices]
# train model
pipeline = train_model(corpus=train_corpus,
pipeline=pipeline,
verbose=0)
save_model(pipeline=pipeline,
output_dir=output_dir + "/",
filename=filename,
verbose=verbosity_level)
# --------------------------------------------------------------------------
# End Execution
if verbosity_level:
print("Training task complete in " + str(round(time() - t0)) +
" s")